Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17921
    Prev
    Next
    INDEX
    Explanations

    timestamps formatted with numbers and colons

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to individuals in a legislative or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totaling
    -0.75
     vulner
    -0.67
    verages
    -0.66
     helicop
    -0.66
    Elect
    -0.64
     totaled
    -0.63
     uniformly
    -0.62
    comb
    -0.61
     shenan
    -0.61
     unprotected
    -0.61
    POSITIVE LOGITS
     <+
    0.85
    dding
    0.78
    sol
    0.75
     Objective
    0.72
     Narr
    0.72
     Edited
    0.71
    meier
    0.70
     Dialogue
    0.69
    avez
    0.69
    illance
    0.68
    Activations Density 0.122%

    No Known Activations